Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
cs.LG, cs.AI
Submitted: 2026-10-08
Updated: 2026-10-14
Code: https://github.com/AlignmentResearch/caught-in-the-act-probes
Sources
- Persona Cartography: Charting Language Model Personality Traits in Weight Space
- Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
- Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
- Discovering Latent Knowledge in Language Models Without Supervision
- Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
- Training Verifiers to Solve Math Word Problems
- "Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms
- Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
- Emergent alignment and the projectability of ethical personas
- Gemma 3 Technical Report
- Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models
- What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams
- Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
- Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
- WikiHow: A Large Scale Text Summarization Dataset
- Building Production-Ready Probes For Gemini
- Liars' Bench: Evaluating Lie Detectors for Language Models
- SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
- The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks